aboutsummaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd
AgeCommit message (Collapse)AuthorFilesLines
2017-08-15drm/amdkfd: Adding new IOCTL for scratch memory v2Moses Reuben5-0/+45
v2: * Renamed ALLOC_MEMORY_OF_SCRATCH to SET_SCRATCH_BACKING_VA * Removed size parameter from the ioctl, it was unused * Removed hole in ioctl number space * No more call to write_config_static_mem * Return correct error code from ioctl Signed-off-by: Moses Reuben <[email protected]> Signed-off-by: Ben Goz <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu: Add kgd/kfd interface to support scratch memory v2Moses Reuben3-2/+34
v2: * Shortened headline * Removed write_config_static_mem, it gets initialized by gfx_v?_0_gpu_init * Renamed alloc_memory_of_scratch to set_scratch_backing_va * Made set_scratch_backing_va a void function * Documented set_scratch_backing in kgd_kfd_interface.h Signed-off-by: Moses Reuben <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu: Program SH_STATIC_MEM_CONFIG globally, not per-VMIDFelix Kuehling2-2/+3
This register only has a single instance in the hardware. Its value applies to all VMIDS. Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amd: Update MEC HQD loading code for KFDFelix Kuehling10-65/+314
Various bug fixes and improvements that accumulated over the last two years. Signed-off-by: Felix Kuehling <[email protected]> Acked-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu: Disable GFX PG on CZFelix Kuehling1-2/+1
It's causing problems with user mode queues and the HIQ, and can lead to hard hangs during boot after programming RLC_CP_SCHEDULERS. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Update PM4 packet headersFelix Kuehling4-414/+199
To match current firmware. The map process packet has been extended to support scratch. This is a non-backwards compatible change and it's about two years old. So no point keeping the old version around conditionally. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Clamp EOP queue size correctly on Gfx8Jay Cornwall1-2/+9
Gfx8 HW incorrectly clamps CP_HQD_EOP_CONTROL.EOP_SIZE, which can lead to scheduling deadlock due to SE EOP done counter overflow. Enforce a EOP queue size limit which prevents the CP from sending more than 0xFF events at a time. Signed-off-by: Jay Cornwall <[email protected]> Reviewed-by: Felix Kuehling <[email protected]> Acked-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Add more error printing to help bringup v2Yong Zhao1-2/+10
v2: Turned WARN into dev_warn and made the message more helpful Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Handle remaining BUG_ONs more gracefully v2Felix Kuehling14-55/+84
In most cases, BUG_ONs can be replaced with WARN_ON with an error return. In some void functions just turn them into a WARN_ON and possibly an early exit. v2: * Cleaned up error handling in pm_send_unmap_queue * Removed redundant WARN_ON in kfd_process_destroy_delayed Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Allocate gtt_sa_bitmap in long unitsFelix Kuehling1-4/+4
gtt_sa_bitmap is accessed by bitmap functions, which operate on longs. Therefore the array should be allocated in long units. Also round up in case the number of bits is not a multiple of BITS_PER_LONG. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Fix doorbell initialization and finalizationFelix Kuehling3-4/+21
Handle errors in doorbell aperture initialization instead of BUG_ON. iounmap doorbell aperture during finalization. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Remove BUG_ONs for NULL pointer argumentsFelix Kuehling15-212/+4
Remove BUG_ONs that check for NULL pointer arguments that are dereferenced in the same function. Dereferencing the NULL pointer will generate a BUG anyway, so the explicit check is redundant and unnecessary overhead. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Remove usage of alloc(sizeof(struct...Kent Russell6-11/+11
See https://kernel.org/doc/html/latest/process/coding-style.html under "14) Allocating Memory" for rationale behind removing the x=alloc(sizeof(struct) style and using x=alloc(sizeof(*x) instead Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Fix goto usage v2Kent Russell5-82/+66
Remove gotos that do not feature any common cleanup, and use gotos instead of repeating cleanup commands. According to kernel.org: "The goto statement comes in handy when a function exits from multiple locations and some common work such as cleanup has to be done. If there is no cleanup needed then just return directly." v2: Applied review suggestions in create_queue_nocpsch Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Change x==NULL/false references to !xKent Russell15-87/+85
Upstream prefers the !x notation to x==NULL or x==false. Along those lines change the ==true or !=NULL references as well. Also make the references to !x the same, excluding () for readability. Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Consolidate and clean up log commandsKent Russell17-236/+158
Consolidate log commands so that dev_info(NULL, "Error...") uses the more accurate pr_err, remove the module name from the log (can be seen via dynamic debugging with +m), and the function name (can be seen via dynamic debugging with +f). We also don't need debug messages saying what function we're in. Those can be added by devs when needed Don't print vendor and device ID in error messages. They are typically the same for all GPUs in a multi-GPU system. So this doesn't add any value to the message. Lastly, remove parentheses around %d, %i and 0x%llX. According to kernel.org: "Printing numbers in parentheses (%d) adds no value and should be avoided." Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Yong Zhao <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Clean up KFD style errors and warnings v2Kent Russell19-78/+91
Using checkpatch.pl -f <file> showed a number of style issues. This patch addresses as many of them as possible. Some long lines have been left for readability, but attempts to minimize them have been made. v2: Broke long lines in gfx_v7 get_fw_version Signed-off-by: Kent Russell <[email protected]> Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu: Remove hard-coded assumptions about compute pipesFelix Kuehling2-3/+3
Remove hard-coded assumption that the first compute pipe is reserved for amdgpu. Pipe 0 actually means pipe 0 now. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Fix allocated_queues bitmap initializationFelix Kuehling1-3/+9
Use shared_resources.queue_bitmap to determine the queues available for KFD in each pipe. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Remove bogus divide-by-sizeof(uint32_t)Felix Kuehling1-8/+0
kfd2kgd->address_watch_get_offset returns dword register offsets. Signed-off-by: Felix Kuehling <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdkfd: Fix typo in dbgdev_wave_reset_wavefrontsFelix Kuehling1-1/+1
Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Oded Gabbay <[email protected]>
2017-08-15drm/amdgpu/gfx7: fix function nameAlex Deucher1-3/+3
Was using the wrong prefix (gmc rather than gfx). The function is related to the gfx hw, not gmc. This also makes it consistent with the naming in gfx8. Reviewed-by: Harry Wentland <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/amdgpu: Disabling Power Gating for Stoney platformVijendar Mukunda1-23/+28
Power Gating is disabled in Stoney platform. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Vijendar Mukunda <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/amdgpu: Added a quirk for Stoney platformVijendar Mukunda1-3/+18
Added DW_I2S_QUIRK_16BIT_IDX_OVERRIDE quirk for Stoney. Supported format and bus width for I2S controller read from I2S Component Parameter registers. These are ready only registers. For Stoney, I2S Component Parameter registers are programmed to support 32 bit format and 4 bytes bus width only. By setting this quirk,It will override 32 bit format with 16 bit format and 2 bytes as bus width for Stoney. Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Vijendar Mukunda <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: jt_size was wrongly counted twiceEvan Quan1-2/+0
Signed-off-by: Evan Quan <[email protected]> Signed-off-by: Huang Rui <[email protected]> Acked-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: fix missing endian-safe guardEvan Quan1-1/+1
Signed-off-by: Evan Quan <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: ignore digest_size when loading sdma fw for ravenHawking Zhang1-14/+0
digest_size has been retired from sdma v4 fw Signed-off-by: Hawking Zhang <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Reviewed-by: Evan Quan <[email protected]> Reviewed-by: Junwei Zhang <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Uninitialized variable in amdgpu_ttm_backend_bind()Dan Carpenter1-1/+1
My static checker complains that it's possible for "r" to be uninitialized. It used to be set to zero so this returns it to the old behavior. Fixes: 98a7f88ce9a9 ("drm/amdgpu: bind BOs with GTT space allocated directly v2") Reviewed-by: Christian König <[email protected]> Reviewed-by: Michel Dänzer <[email protected]> Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: fix coding style in hwmgr.cRex Zhu1-7/+7
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: refine dmesg info under powerplay.Rex Zhu2-8/+7
Use pr_debug to prevent spamming unimportant dmesg. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: don't finish the ring if not initializedTrigger Huang1-0/+4
If a ring is not initialized, it also should not be finished. For example, in Vega10's SR-IOV environment, UVD's decode ring is not initialized, but will be finnished in amdgpu_uvd_sw_fini, because UVD driver put all the uvd decode ring's finish operation into amdgpu_uvd_sw_fini function, while not uvd_vXXX_0_sw_fini. This will lead to amdgpu module unloading failure. Signed-off-by: Trigger Huang <[email protected]> Reviewed-by: Monk Liu <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix preferred typoKent Russell7-16/+16
Change "prefered" to "preferred" Signed-off-by: Kent Russell <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix stolen typoKent Russell2-7/+7
Change "stollen" to "stolen" Signed-off-by: Kent Russell <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: fix coccinelle warnings in vega10_hwmgr.cRex Zhu1-1/+1
delete unneeded semicolon. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: set gfx_v9_0_ip_funcs as staticHuang Rui2-2/+1
We won't use this member in other files, so set it static. Signed-off-by: Huang Rui <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: switch to drm_*{get,put} helpersCihangir Akturk9-30/+30
drm_*_reference() and drm_*_unreference() functions are just compatibility alias for drm_*_get() and drm_*_put() and should not be used by new code. So convert all users of compatibility functions to use the new APIs. Reviewed-by: Christian König <[email protected]> Signed-off-by: Cihangir Akturk <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: add CZ profile supportAlex Deucher1-2/+80
Support the profiling modes for sclk. v2: delete profileing mode for mclk. Signed-off-by: Alex Deucher <[email protected]> Signed-off-by: Rex Zhu <[email protected]> Tested-and-Reviewed-by Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: fix PSI not enabled by kmdRex Zhu2-1/+4
cherry-pick from windows driver. Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: fix set highest mclk level failed on Vega10Rex Zhu1-6/+27
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amd/powerplay: fix force dpm level failed on CZRex Zhu1-16/+21
Signed-off-by: Rex Zhu <[email protected]> Reviewed-by: Alex Deucher <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: use 256 bit buffers for all wb allocations (v2)Alex Deucher3-126/+20
May waste a bit of memory, but simplifies the interface significantly. v2: convert internal accounting to use 256bit slots Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Make amdgpu_atif_handler staticJean Delvare1-1/+1
There are no external users of function amdgpu_atif_handler so it can be static. Signed-off-by: Jean Delvare <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix amdgpu_pm_acpi_event_handler warningJean Delvare2-1/+2
Include a missing header to get rid of the following warning: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c:65:6: warning: no previous prototype for ‘amdgpu_pm_acpi_event_handler’ [-Wmissing-prototypes] void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev) ^ Signed-off-by: Jean Delvare <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix dce_v6_0_disable_dce warningJean Delvare1-0/+1
Include a missing header to get rid of the following warning: drivers/gpu/drm/amd/amdgpu/dce_v6_0.c:521:6: warning: no previous prototype for 'dce_v6_0_disable_dce' [-Wmissing-prototypes] void dce_v6_0_disable_dce(struct amdgpu_device *adev) ^ Signed-off-by: Jean Delvare <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Christian König" <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix undue fallthroughs in golden registers initializationJean Delvare1-0/+2
As I was staring at the si_init_golden_registers code, I noticed that the Pitcairn initialization silently falls through the Cape Verde initialization, and the Oland initialization falls through the Hainan initialization. However there is no comment stating that this is intentional, and the radeon driver doesn't have any such fallthrough, so I suspect this is not supposed to happen. Signed-off-by: Jean Delvare <[email protected]> Fixes: 62a37553414a ("drm/amdgpu: add si implementation v10") Cc: Ken Wang <[email protected]> Cc: Alex Deucher <[email protected]> Cc: "Marek Olšák" <[email protected]> Cc: "Christian König" <[email protected]> Cc: Flora Cui <[email protected]> Reviewed-by: Marek Olšák <[email protected]> Signed-off-by: Alex Deucher <[email protected]> Cc: [email protected]
2017-08-15drm/amdgpu/sdma4: move wptr polling setupAlex Deucher1-11/+13
Move it up before ring enablement with all of the other engine setup and explicitly disable it for bare metal. Cc: Frank Min <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu/sdma4: drop allocation of poll_mem_offsAlex Deucher2-37/+9
We already allocate this as part of the ring structure, use that instead. Cc: Frank Min <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu/sdma4: drop hdp flush from wptr shadow updateAlex Deucher1-1/+0
The wb buffer is in system memory, not vram so the flush is useless. Cc: Frank Min <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu/sdma4: set wptr shadow atomically (v2)Alex Deucher1-2/+3
No functional change until wptr polling uses this location (future patch). v2: use WRITE_ONCE Cc: Frank Min <[email protected]> Reviewed-by: Christian König <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
2017-08-15drm/amdgpu: Fix KFD initialization for multi-GPU systemsFelix Kuehling3-22/+18
kfd2kgd is device-specific, so it should not be a global variable. Merge amdgpu_amdkfd_load_interface and amdgpu_amdkfd_device_probe so that it's only needed as a local variable in one function. Signed-off-by: Felix Kuehling <[email protected]> Reviewed-by: Oded Gabbay <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.